Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true and openWorldHint=false, and the description is consistent with them rather than repeating them. It adds genuinely useful behavior beyond the structured fields: the tool returns procedural instructions rather than performing an action, opens nothing itself, and requires a separate Cloud Browser session to execute the refund. It does not cover what happens if no Cloud Browser session exists or whether any authentication is required.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The important constraint ('opens nothing by itself,' use the browser tools afterward) is front-loaded and earns its place, but 'from ChatGPT, Claude or any AI agent' is marketing filler and 'WooCommerce's official API: Yes' is ambiguous shorthand that adds little or no information. Trimming those would make the definition materially tighter.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter instruction-emitting tool with read-only/idempotent annotations and no output schema, the description covers what it returns and how to act on it. The one real omission is the prerequisite state of the Cloud Browser session (whether the agent must first call cotlet_browser_open), which would matter in practice.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has zero parameters and additionalProperties is false, so there is no parameter meaning for the description to add. The 0-parameter baseline of 4 applies; nothing in the description misleads about inputs.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource and, crucially, clarifies that this is a non-executing guidance tool: 'Returns how to do it in WooCommerce step by step (screens, buttons, fields) and opens nothing by itself.' That resolves the tension with the name 'create_refund,' which alone would imply an actual write. It stops short of a fully crisp one-line statement of purpose because it spends words on the AI-agent framing and the cryptic 'WooCommerce's official API: Yes.'

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives a clear usage path: call this to get the click-by-click procedure, then 'do it with the cotlet_browser_* tools in the user's WooCommerce Cloud Browser.' That tells the agent both when to use it and what the follow-on action is. It does not mention when not to use it or how it relates to the other woocommerce_* siblings (e.g., whether any of them can perform the refund directly), so no explicit exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.